huggingchat/papers-content
7.57 GB
HuggingChat
community
AI & ML interests
None defined yet.
Recent Activity
View all activity
mishigÂ
updated a
bucket 1 day ago
CarolinePascalÂ
authored 2
papers 13 days ago
Post
5764
who's working on an NVFP4 version of Kimi-K3?
- 4 replies
Post
6041
Sharing how I built the LongCat-Video-Avatar 1.5 Space (+500k views on X) in one agent session. Gave a coding agent its own AI lab on ZeroGPU, framed the goal, walked away. It designed, deployed, tested against the live API, fixed, shipped.
Full recipe with the copy-paste prompt: https://huggingface.co/blog/victor/building-zerogpu-spaces-autonomously
Full recipe with the copy-paste prompt: https://huggingface.co/blog/victor/building-zerogpu-spaces-autonomously
- 1 reply
Post
6339
Want to share my enthusiasm for zai-org/GLM-5.1 here too đĽ
I think we have it: our open source Claude Code = GLM-5.1 + Pi (https://pi.dev/) - Built a Three.js racing game to eval and it's extremely impressive. Thoughts:
- One-shot car physics with real drift mechanics (this is hard)
- My fav part: Awesome at self iterating (with no vision!) created 20+ Bun.WebView debugging tools to drive the car programmatically and read game state. Proved a winding bug with vector math without ever seeing the screen
- 531-line racing AI in a single write: 4 personalities, curvature map, racing lines, tactical drifting. Built telemetry tools to compare player vs AI speed curves and data-tuned parameters
- All assets from scratch: 3D models, procedural textures, sky shader, engine sounds, spatial AI audio!
- Can do hard math: proved road normals pointed DOWN via vector cross products, computed track curvature normalized by arc length to tune AI cornering speed
You are going to hear about this model a lot in the next months - open source let's go - and thanks z-aiđđ
I think we have it: our open source Claude Code = GLM-5.1 + Pi (https://pi.dev/) - Built a Three.js racing game to eval and it's extremely impressive. Thoughts:
- One-shot car physics with real drift mechanics (this is hard)
- My fav part: Awesome at self iterating (with no vision!) created 20+ Bun.WebView debugging tools to drive the car programmatically and read game state. Proved a winding bug with vector math without ever seeing the screen
- 531-line racing AI in a single write: 4 personalities, curvature map, racing lines, tactical drifting. Built telemetry tools to compare player vs AI speed curves and data-tuned parameters
- All assets from scratch: 3D models, procedural textures, sky shader, engine sounds, spatial AI audio!
- Can do hard math: proved road normals pointed DOWN via vector cross products, computed track curvature normalized by arc length to tune AI cornering speed
You are going to hear about this model a lot in the next months - open source let's go - and thanks z-aiđđ
- 5 replies
victorÂ
submitted a
paper to Daily Papers 7 months ago
julien-cÂ
submitted a
paper to Daily Papers 8 months ago
Post
2906
Interesting article: use Claude Code to help open models write CUDA kernels (for eg) by turning CC traces into Skills. They made a library out of it đ
https://huggingface.co/blog/upskill
https://huggingface.co/blog/upskill
Post
3641
Nvidia is on a roll lately. Nemotron 3 Nano is my new fav local model, but here's the real flex: they published the entire evaluation setup. Configs, prompts, logs, all of it. This is how you do open models đĽ
https://huggingface.co/blog/nvidia/nemotron-3-nano-evaluation-recipe
https://huggingface.co/blog/nvidia/nemotron-3-nano-evaluation-recipe
Post
1766
The #1 trending AI/ML dataset today đ
Massive scale, diversity and end-to-end potential from nvidia !
nvidia/PhysicalAI-Autonomous-Vehicles
Massive scale, diversity and end-to-end potential from nvidia !
nvidia/PhysicalAI-Autonomous-Vehicles
- 1 reply
Post
909
The new King đhas arrived!
Moonshot AI now the top model on Hugging Face đĽ
moonshotai/Kimi-K2-Thinking
Moonshot AI now the top model on Hugging Face đĽ
moonshotai/Kimi-K2-Thinking
Post
2942
đ¸đ¤You donât need 100 GPUs to train something amazing!
Our Smol Training Playbook teaches you a better path to world-class LLMs, for free!
Check out the #1 trending space on đ¤ :
HuggingFaceTB/smol-training-playbook
Our Smol Training Playbook teaches you a better path to world-class LLMs, for free!
Check out the #1 trending space on đ¤ :
HuggingFaceTB/smol-training-playbook
Post
2404
Cool stuff these past weeks on huggingface! đ¤ đ !
⢠đTrackio, local-first W&B alternative
https://github.com/gradio-app/trackio/issues
⢠đEmbeddingGemma, 300M-param, multilingual embeddings, on-device
https://huggingface.co/blog/embeddinggemma
⢠đťOpen LLMs in VS Code (Inference Providers)
https://x.com/reach_vb/status/1966185427582497171
⢠đ¤Smol2Operator GUI agents
https://huggingface.co/blog/smol2operator
⢠đźď¸Gradio visible watermarking
https://huggingface.co/blog/watermarking-with-gradio
⢠đTrackio, local-first W&B alternative
https://github.com/gradio-app/trackio/issues
⢠đEmbeddingGemma, 300M-param, multilingual embeddings, on-device
https://huggingface.co/blog/embeddinggemma
⢠đťOpen LLMs in VS Code (Inference Providers)
https://x.com/reach_vb/status/1966185427582497171
⢠đ¤Smol2Operator GUI agents
https://huggingface.co/blog/smol2operator
⢠đźď¸Gradio visible watermarking
https://huggingface.co/blog/watermarking-with-gradio
Post
861
GH200 cooking time đ§âđłđĽ!
We just updated GPU-fryer đł to run on Grace Hopper Superchip (GH200) - fully optimized for ARM-based systems!
With this release, we switched to cuBLASLt to support running FP8 benchmarks. You can monitor GPU throttling, TFLOPS outliers, HBM memory health, and ensure that you get the most of your hardware setup.
Perfect for stress testing and tuning datacenter GPUs.
Check it out on Github đ https://github.com/huggingface/gpu-fryer
We just updated GPU-fryer đł to run on Grace Hopper Superchip (GH200) - fully optimized for ARM-based systems!
With this release, we switched to cuBLASLt to support running FP8 benchmarks. You can monitor GPU throttling, TFLOPS outliers, HBM memory health, and ensure that you get the most of your hardware setup.
Perfect for stress testing and tuning datacenter GPUs.
Check it out on Github đ https://github.com/huggingface/gpu-fryer
Post
7672
Open Source Avengers, Assemble! Ask an expert AI agent team to solve complex problems together đĽ
Consilium brings together multiple agents that debate and use live research (web, arXiv, SEC) to reach a consensus. You set the strategy, they find the answer.
Credit to @azettl for this awesome demo: Agents-MCP-Hackathon/consilium_mcp
Consilium brings together multiple agents that debate and use live research (web, arXiv, SEC) to reach a consensus. You set the strategy, they find the answer.
Credit to @azettl for this awesome demo: Agents-MCP-Hackathon/consilium_mcp
- 2 replies
CarolinePascalÂ
authored a
paper over 1 year ago
Post
12031
BOOOOM: Today I'm dropping TINY AGENTS
the 50 lines of code Agent in Javascript đĽ
I spent the last few weeks working on this, so I hope you will like it.
I've been diving into MCP (Model Context Protocol) to understand what the hype was all about.
It is fairly simple, but still quite powerful: MCP is a standard API to expose sets of Tools that can be hooked to LLMs.
But while doing that, came my second realization:
Once you have a MCP Client, an Agent is literally just a while loop on top of it. đ¤Ż
âĄď¸ read it exclusively on the official HF blog: https://huggingface.co/blog/tiny-agents
the 50 lines of code Agent in Javascript đĽ
I spent the last few weeks working on this, so I hope you will like it.
I've been diving into MCP (Model Context Protocol) to understand what the hype was all about.
It is fairly simple, but still quite powerful: MCP is a standard API to expose sets of Tools that can be hooked to LLMs.
But while doing that, came my second realization:
Once you have a MCP Client, an Agent is literally just a while loop on top of it. đ¤Ż
âĄď¸ read it exclusively on the official HF blog: https://huggingface.co/blog/tiny-agents
- 1 reply
Post
5222
- 1 reply